Home Big Data Mining and Analytics Article
PDF (7.1 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Open Access

Photovoltaic Power Forecasting with Weather Conditioned Attention Mechanism

School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China
Gansu Provincial Industry Technology Center of Intelligent Equipment & Big Data for Disaster Prevention, Northwest Institute of Eco-Environmentand Resources, Chinese Academy of Sciences, Lanzhou 730000, China
Show Author Information

Abstract

Accurate Photovoltaic (PV) generation forecasts can reduce power redeploy from the grid, thus increasing the supplier’s profit in the day-ahead electricity market. However, the PV process is affected differently by various factors under different weather conditions, resulting in significantly different energy output curves. In this context, this paper proposes a day-ahead PV power forecasting method with weather conditioned attention mechanism. We propose a Multi-Stream Attention Fusion Network (MSAFN) which utilizes an algorithm to derive the optimal decomposition algorithm for different weather conditions. The proposed Conditional Decomposition (CD) algorithm searches for the decomposition algorithms and corresponding hyperparameters of the prediction model, aiming to achieve the optimal prediction performance. The MSAFN incorporates multiple attention modules to learn the energy output patterns under various weather conditions. Notably, the attention modules adeptly learn patterns under diverse conditions, while simultaneously, the sharing of weights among the remaining components of the model effectively enhances prediction accuracy and facilitates a reduction in training time. We compare the state-of-the-art decomposition algorithms (VMD, EEMD, MSTL, etc.) and prediction models (BPN, LSTM, XGBoost, transformer, etc.) commonly used in PV prediction. The results show that the MSAFN model is more accurate than the models above, which has a noticeable improvement compared to other recent day-ahead PV predictions on Desert Knowledge Australia Solar Centre (DKASC) dataset.

Keywords

Photovoltaic (PV) forecastingdeep learningtransformerDesert Knowledge Australia Solar Centre (DKASC)

References

[1]
International Energy Agency, Greenhouse gas emissions from energy data explorer, https://www.iea.org/data-and-statistics/data-tools/greenhouse-gas-emissions-from-energy-data-explorer, 2021.
[2]
EPA, Renewable energy in corporate greenhouse gas emissions inventory, https://www.epa.gov/green-power-markets/renewable-energy-corporate-greenhouse-gas-emissions-inventory, 2022.
[3]
International Energy Agency, Snapshot 2022, https://iea-pvps.org/snapshot-reports/snapshot-2022/, 2022.
[4]
P. Mathiesen, J. Kleissl, and C. Collier, Case studies of solar forecasting with the weather research and forecasting model at GL-Garrad Hassan, in Solar Energy Forecasting and Resource Assessment, Jan Kleissl, ed. Boston, MA, USA: Academic Press, 2013, pp. 357–382.
[5]

J. Antonanzas, N. Osorio, R. Escobar, R. Urraca, F. J. Martinez-de-Pison, and F. Antonanzas-Torres, Review of photovoltaic power forecasting, Sol. Energy, vol. 136, pp. 78–111, 2016.

Crossref Google Scholar
[6]

E. Lorenz, T. Scheidsteger, J. Hurka, D. Heinemann, and C. Kurz, Regional PV power prediction for improved grid integration, Prog. Photovolt. Res. Appl., vol. 19, no. 7, pp. 757–771, 2011.

Crossref Google Scholar
[7]

S. Pelland, G. Galanis, and G. Kallos, Solar and photovoltaic forecasting through post-processing of the global environmental multiscale numerical weather prediction model, Prog. Photovolt. Res. Appl., vol. 21, no. 3, pp. 284–296, 2013.

Crossref Google Scholar
[8]

J. Alonso-Montesinos and F. J. Batlles, Solar radiation forecasting in the short- and medium-term under all sky conditions, Energy, vol. 83, pp. 387–393, 2015.

Crossref Google Scholar
[9]

C. S. Lai, C. Zhong, K. Pan, W. W. Y. Ng, and L. L. Lai, A deep learning based hybrid method for hourly solar radiation forecasting, Expert Syst. Appl., vol. 177, p. 114941, 2021.

Crossref Google Scholar
[10]

U. K. Das, K. S. Tey, M. Seyedmahmoudian, S. Mekhilef, M. Y. I. Idris, W. Van Deventer, B. Horan, and A. Stojcevski, Forecasting of photovoltaic power generation and model optimization: A review, Renew. Sustain. Energy Rev., vol. 81, pp. 912–928, 2018.

Crossref Google Scholar
[11]

M. Kudo, A. Takeuchi, Y. Nozaki, H. Endo, and J. Sumita, Forecasting electric power generation in a photovoltaic power system for an energy network, Electr. Eng. Jpn., vol. 167, no. 4, pp. 16–23, 2009.

Crossref Google Scholar
[12]

S. Sobri, S. Koohi-Kamali, and N. A. Rahim, Solar photovoltaic generation forecasting methods: A review, Energy Convers. Manag., vol. 156, pp. 459–497, 2018.

Crossref Google Scholar
[13]

M. J. Mayer, Benefits of physical and machine learning hybridization for photovoltaic power forecasting, Renew. Sustain. Energy Rev., vol. 168, p. 112772, 2022.

Crossref Google Scholar
[14]

F. J. L. Lima, F. R. Martins, E. B. Pereira, E. Lorenz, and D. Heinemann, Forecast for surface solar irradiance at the Brazilian Northeastern region using NWP model and artificial neural networks, Renew. Energy, vol. 87, pp. 807–818, 2016.

Google Scholar
[15]
Q. Song, F. Li, J. Qian, J. Zhao, and Z. Chen, Photovoltaic power prediction based on principal component analysis and support vector machine, in Proc. IEEE Innovative Smart Grid Technologies—Asia (ISGT-Asia), Melbourne, Australia, 2016, pp. 815–820.
[16]

F. Almonacid, P. J. Pérez-Higueras, E. F. Fernández, and L. Hontoria, A methodology based on dynamic artificial neural network for short-term forecasting of the power output of a PV generator, Energy Convers. Manag., vol. 85, pp. 389–398, 2014.

Crossref Google Scholar
[17]
T. T. Teo, T. Logenthiran, and W. L. Woo, Forecasting of photovoltaic power using extreme learning machine, in Proc. IEEE Innovative Smart Grid Technologies—Asia (ISGT Asia), Bangkok, Thailand, 2015, pp. 1–6.
[18]

M. AlShafeey and C. Csáki, Evaluating neural network and linear regression photovoltaic power forecasting models based on different input methods, Energy Rep., vol. 7, pp. 7601–7614, 2021.

Crossref Google Scholar
[19]

M. Gao, J. Li, F. Hong, and D. Long, Day-ahead power forecasting in a large-scale photovoltaic plant based on weather classification using LSTM, Energy, vol. 187, p. 115838, 2019.

Crossref Google Scholar
[20]
A. Agga, A. Abbou, M. Labbadi, and Y. El Houm, Convolutional neural network (CNN) extended architectures for photovoltaic power production forecasting, in Proc. 9th Int. Conf. Smart Grid and Clean Energy Technologies (ICSGCE), Sarawak, Malaysia, 2021, pp. 104–108.
[21]

U. Munawar and Z. Wang, A framework of using machine learning approaches for short-term solar power forecasting, J. Electr. Eng. Technol., vol. 15, no. 2, pp. 561–569, 2020.

Crossref Google Scholar
[22]

M. L. Santos, X. García-Santiago, F. E. Camarero, G. B. Gil, and P. C. Ortega, Application of temporal fusion transformer for day-ahead PV power forecasting, Energies, vol. 15, no. 14, p. 5232, 2022.

Crossref Google Scholar
[23]
DKASC, Alice Springs, https://dkasolarcentre.com.au/locations/alicesprings, 2008.
[24]
A. Bracale, P. Caramia, G. Carpinelli, A. Di Fazio, and G. Ferruzzi, A Bayesian method for short-term probabilistic forecasting of photovoltaic generation in smart grid operation and control, Energies, vol. 6, no. 2, pp. 733–747, 2013.
[25]

Aasim, S. N. Singh, and A. Mohapatra, Repeated wavelet transform based ARIMA model for very short-term wind speed forecasting, Renewable Energy, vol. 136, pp. 758–768, 2019.

Crossref Google Scholar
[26]
A. Agga, A. Abbou, M. Labbadi, Y. El Houm, and I. H. Ou Ali, CNN-LSTM: An efficient hybrid deep learning architecture for predicting short-term photovoltaic power production, Electr. Power Syst. Res., vol. 208, p. 107908, 2022.
[27]

A. Agga, A. Abbou, M. Labbadi, and Y. El Houm, Short-term self consumption PV plant power production forecasts based on hybrid CNN-LSTM, ConvLSTM models, Renew. Energy, vol. 177, pp. 101–112, 2021.

Crossref Google Scholar
[28]

Z. Zhen, J. Liu, Z. Zhang, F. Wang, H. Chai, Y. Yu, X. Lu, T. Wang, and Y. Lin, Deep learning based surface irradiance mapping model for solar PV power forecasting using sky image, IEEE Trans. Ind. Appl., vol. 56, no. 4, pp. 3385–3396, 2020.

Google Scholar
[29]

D. Yang, W. Wang, and X. Xia, A concise overview on solar resource assessment and forecasting, Adv. Atmos. Sci., vol. 39, no. 8, pp. 1239–1251, 2022.

Crossref Google Scholar
[30]

D. Yang, A guideline to solar forecasting research practice: Reproducible, operational, probabilistic or physically-based, ensemble, and skill (ROPES), J. Renew. Sustain. Energy, vol. 11, no. 2, p. 022701, 2019.

Crossref Google Scholar
[31]

B. Wolff, J. Kühnert, E. Lorenz, O. Kramer, and D. Heinemann, Comparing support vector regression for PV power forecasting to a physical modeling approach using measurement, numerical weather prediction, and cloud motion data, Sol. Energy, vol. 135, p. 197–208, 2016.

Crossref Google Scholar
[32]

R. A. A. Ramadhan, Y. R. J. Heatubun, S. F. Tan, and H. J. Lee, Comparison of physical and machine learning models for estimating solar irradiance and photovoltaic power, Renewable Energy, vol. 178, pp. 1006–1019, 2021.

Crossref Google Scholar
[33]

F. H. Gandoman, S. H. E. Abdel Aleem, N. Omar, A. Ahmadi, and F. Q. Alenezi, Short-term solar power forecasting considering cloud coverage and ambient temperature variation effects, Renew. Energy, vol. 123, pp. 793–805, 2018.

Crossref Google Scholar
[34]

M. Q. Raza and A. Khosravi, A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings, Renew. Sustain. Energy Rev., vol. 50, pp. 1352–1372, 2015.

Crossref Google Scholar
[35]

M. Q. Raza, M. Nadarajah, and C. Ekanayake, On recent advances in PV output power forecast, Sol. Energy, vol. 136, pp. 125–144, 2016.

Crossref Google Scholar
[36]

Z. Csereklyei, S. Qu, and T. Ancev, The effect of wind and solar power generation on wholesale electricity prices in Australia, Energy Policy, vol. 131, pp. 358–369, 2019.

Crossref Google Scholar
[37]

V. M. Puri, Estimation of half-hour solar radiation values from hourly values, Sol. Energy, vol. 21, no. 5, pp. 409–414, 1978.

Crossref Google Scholar
[38]

P. Bacher, H. Madsen, and H. A. Nielsen, Online short-term solar power forecasting, Sol. Energy, vol. 83, no. 10, pp. 1772–1783, 2009.

Crossref Google Scholar
[39]

A. Mellit and A. M. Pavan, A 24-h forecast of solar irradiance using artificial neural network: Application for performance prediction of a grid-connected PV plant at Trieste, Italy, Sol. Energy, vol. 84, no. 5, pp. 807–821, 2010.

Crossref Google Scholar
[40]

W. Lin, B. Zhang, H. Li, and R. Lu, Multi-step prediction of photovoltaic power based on two-stage decomposition and BILSTM, Neurocomputing, vol. 504, pp. 56–67, 2022.

Crossref Google Scholar
[41]

X. Zhang, Y. Li, S. Lu, H. F. Hamann, B. M. Hodge, and B. Lehman, A solar time based analog ensemble method for regional solar power forecasting, IEEE Trans. Sustain. Energy, vol. 10, no. 1, pp. 268–279, 2019.

Crossref Google Scholar
[42]

M. N. Akhter, S. Mekhilef, H. Mokhlis, R. Ali, M. Usama, M. A. Muhammad, and A. S. M. Khairuddin, A hybrid deep learning method for an hour ahead power output forecasting of three different photovoltaic systems, Appl. Energy, vol. 307, p. 118185, 2022.

Crossref Google Scholar
[43]

L. M. Ayompe, A. Duffy, S. J. McCormack, and M. Conlon, Validated real-time energy models for small-scale grid-connected PV-systems, Energy, vol. 35, no. 10, pp. 4086–4091, 2010.

Crossref Google Scholar
[44]

J. Qu, Z. Qian, and Y. Pei, Day-ahead hourly photovoltaic power forecasting using attention-based CNN-LSTM neural network embedded with multiple relevant and target variables prediction pattern, Energy, vol. 232, p. 120996, 2021.

Crossref Google Scholar
[45]

Z. A. Khan, T. Hussain, and S. W. Baik, Dual stream network with attention mechanism for photovoltaic power forecasting, Appl. Energy, vol. 338, p. 120916, 2023.

Crossref Google Scholar
[46]

Y. Liu, Y. Liu, H. Cai, and J. Zhang, An innovative short-term multihorizon photovoltaic power output forecasting method based on variational mode decomposition and a capsule convolutional neural network, Appl. Energy, vol. 343, p. 121139, 2023.

Crossref Google Scholar
[47]

B. Gu, H. Shen, X. Lei, H. Hu, and X. Liu, Forecasting and uncertainty analysis of day-ahead photovoltaic power using a novel forecasting method, Appl. Energy, vol. 299, p. 117291, 2021.

Crossref Google Scholar
[48]

F. Wang, Z. Xuan, Z. Zhen, K. Li, T. Wang, and M. Shi, A day-ahead PV power forecasting method based on LSTM-RNN model and time correlation modification under partial daily pattern prediction framework, Energy Convers. Manag., vol. 212, p. 112766, 2020.

Crossref Google Scholar
[49]
S. M. Miraftabzadeh, M. Longo, and F. Foiadelli, A-day-ahead photovoltaic power prediction based on long short term memory algorithm, in Proc. Int. Conf. Smart Energy Systems and Technologies (SEST), Istanbul, Turkey, 2020, pp. 1–6.
[50]

S. Theocharides, G. Makrides, A. Livera, M. Theristis, P. Kaimakis, and G. E. Georghiou, Day-ahead photovoltaic power production forecasting methodology based on machine learning and statistical post-processing, Appl. Energy, vol. 268, p. 115023, 2020.

Crossref Google Scholar
[51]
Solar geometry calculator, https://gml.noaa.gov/grad/antuv/SolarCalc.jsp, 2020.
[52]

H. Zang, L. Cheng, T. Ding, K. W. Cheung, Z. Wei, and G. Sun, Day-ahead photovoltaic power forecasting approach based on deep convolutional neural networks and meta learning, Int. J. Electr. Power Energy Syst., vol. 118, p. 105790, 2020.

Crossref Google Scholar
[53]

V. R. Carvalho, M. F. D. Moraes, A. P. Braga, and E. M.A.M. Mendes, Evaluating five different adaptive decomposition methods for EEG signal seizure detection and classification, Biomedical Signal Processing and Control, vol. 62, p. 102073, 2020.

Crossref Google Scholar
[54]
O. Pele and M. Werman, A linear time histogram metric for improved SIFT matching, in Computer Vision–ECCV 2008, D. Forsyth, P. Torr, and A. Zisserman, eds. Berlin, Germany: Springer, 2008, pp. 495–508.
[55]
M. V. Ronkin, A. A. Kalmykov, S. O. Polyakov, and V. S. Nagovicin, Numerical analysis of adaptive signal decomposition methods applied for ultrasonic gas flowmeters, in Proc. Int. Conf. Numerical Analysis and Applied Mathematics ICNAAM 2020, Rhodes, Greece, 2022, p. 130009.
[56]
S. Seabold and J. Perktold, Statsmodels: Econometric and statistical modeling with Python, https://doi.org/10.25080/Majora-92bf1922-011, 2010.
Crossref
[57]
R. J Lewis, An introduction to classification and regression tree (CART) analysis, presented at the 2000 Annual Meeting of the Society for Academic Emergency Medicine, San Francisco, CA, USA, 2000.
[58]
T. Chen and C. Guestrin, XGBoost: A scalable tree boosting system, in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 785–794.
[59]
N. Zhai, P. Yao, and X. Zhou, Multivariate time series forecast in industrial process based on XGBoost and GRU, in Proc. IEEE 9th Joint Int. Information Technology and Artificial Intelligence Conf. (ITAIC), Chongqing, China, 2020, pp. 1397–1400.
Big Data Mining and Analytics
Volume 8 Issue 2,
April 2025
Pages 326-345
DOI: 10.26599/BDMA.2024.9020066
Cite this article:
Jiang X, Gou Y, Jiang M, et al. Photovoltaic Power Forecasting with Weather Conditioned Attention Mechanism. Big Data Mining and Analytics, 2025, 8(2): 326-345. https://doi.org/10.26599/BDMA.2024.9020066
Metrics & Citations  
Article History
Copyright
Rights and Permissions
Return